library(tidyverse) # for data cleaning and plotting
library(lubridate) # for date manipulation
library(openintro) # for the abbr2state() function
library(palmerpenguins)# for Palmer penguin data
library(maps) # for map data
library(ggmap) # for mapping points on maps
library(gplots) # for col2hex() function
library(RColorBrewer) # for color palettes
library(sf) # for working with spatial data
library(leaflet) # for highly customizable mapping
library(carData) # for Minneapolis police stops data
library(ggthemes) # for more themes (including theme_map())
theme_set(theme_minimal())
# Starbucks locations
Starbucks <- read_csv("https://www.macalester.edu/~ajohns24/Data/Starbucks.csv")
starbucks_us_by_state <- Starbucks %>%
filter(Country == "US") %>%
count(`State/Province`) %>%
mutate(state_name = str_to_lower(abbr2state(`State/Province`)))
# Lisa's favorite St. Paul places - example for you to create your own data
favorite_stp_by_lisa <- tibble(
place = c("Home", "Macalester College", "Adams Spanish Immersion",
"Spirit Gymnastics", "Bama & Bapa", "Now Bikes",
"Dance Spectrum", "Pizza Luce", "Brunson's"),
long = c(-93.1405743, -93.1712321, -93.1451796,
-93.1650563, -93.1542883, -93.1696608,
-93.1393172, -93.1524256, -93.0753863),
lat = c(44.950576, 44.9378965, 44.9237914,
44.9654609, 44.9295072, 44.9436813,
44.9399922, 44.9468848, 44.9700727)
)
#COVID-19 data from the New York Times
covid19 <- read_csv("https://raw.githubusercontent.com/nytimes/covid-19-data/master/us-states.csv")
If you were not able to get set up on GitHub last week, go here and get set up first. Then, do the following (if you get stuck on a step, don’t worry, I will help! You can always get started on the homework and we can figure out the GitHub piece later):
keep_md: TRUE in the YAML heading. The .md file is a markdown (NOT R Markdown) file that is an interim step to creating the html file. They are displayed fairly nicely in GitHub, so we want to keep it and look at it there. Click the boxes next to these two files, commit changes (remember to include a commit message), and push them (green up arrow).Put your name at the top of the document.
For ALL graphs, you should include appropriate labels.
Feel free to change the default theme, which I currently have set to theme_minimal().
Use good coding practice. Read the short sections on good code with pipes and ggplot2. This is part of your grade!
When you are finished with ALL the exercises, uncomment the options at the top so your document looks nicer. Don’t do it before then, or else you might miss some important warnings and messages.
These exercises will reiterate what you learned in the “Mapping data with R” tutorial. If you haven’t gone through the tutorial yet, you should do that first.
ggmap)Starbucks locations to a world map. Add an aesthetic to the world map that sets the color of the points according to the ownership type. What, if anything, can you deduce from this visualization?# Get the map information
world <- get_stamenmap(
bbox = c(left = -180, bottom = -57, right = 179, top = 82.1),
maptype = "terrain",
zoom = 2)
ggmap(world) + # creates the map "background"
geom_point(data = Starbucks,
aes(x = Longitude, y = Latitude, color = `Ownership Type`),
alpha = .3,
size = .2) +
theme_map() +
labs(title = "Starbucks Ownership Around the World")
Based on the visualization above, Starbucks in North and South America are mostly Company Owned and Licensed. In Asia and Europe, however, there are many Joint Venture Starbucks in addition to Company Owned and Licensed Starbucks.
twincities <- get_stamenmap(
bbox = c(left = -93.4471, bottom = 44.8173, right = -92.7838, top = 45.1316),
maptype = "terrain",
zoom = 11)
ggmap(twincities) + # creates the map "background"
geom_point(data = Starbucks,
aes(x = Longitude, y = Latitude),
alpha = 1,
size = 2) +
labs(title = "Starbucks in the Twin Cities",
x = "Longitude",
y = "Latitude")
theme_map()
## List of 93
## $ line :List of 6
## ..$ colour : chr "black"
## ..$ size : num 0.409
## ..$ linetype : num 1
## ..$ lineend : chr "butt"
## ..$ arrow : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_line" "element"
## $ rect :List of 5
## ..$ fill : chr "white"
## ..$ colour : chr "black"
## ..$ size : num 0.409
## ..$ linetype : num 1
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ text :List of 11
## ..$ family : chr ""
## ..$ face : chr "plain"
## ..$ colour : chr "black"
## ..$ size : num 9
## ..$ hjust : num 0.5
## ..$ vjust : num 0.5
## ..$ angle : num 0
## ..$ lineheight : num 0.9
## ..$ margin : 'margin' num [1:4] 0points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ title : NULL
## $ aspect.ratio : NULL
## $ axis.title : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ axis.title.x :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 2.25points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.title.x.top :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 0
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 2.25points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.title.x.bottom : NULL
## $ axis.title.y :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 1
## ..$ angle : num 90
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 2.25points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.title.y.left : NULL
## $ axis.title.y.right :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 0
## ..$ angle : num -90
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 0points 2.25points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ axis.text.x :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 1.8points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text.x.top :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 0
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 1.8points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text.x.bottom : NULL
## $ axis.text.y :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 1
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 1.8points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text.y.left : NULL
## $ axis.text.y.right :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 0
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 0points 1.8points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.ticks : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ axis.ticks.x : NULL
## $ axis.ticks.x.top : NULL
## $ axis.ticks.x.bottom : NULL
## $ axis.ticks.y : NULL
## $ axis.ticks.y.left : NULL
## $ axis.ticks.y.right : NULL
## $ axis.ticks.length : 'simpleUnit' num 2.25points
## ..- attr(*, "unit")= int 8
## $ axis.ticks.length.x : NULL
## $ axis.ticks.length.x.top : NULL
## $ axis.ticks.length.x.bottom: NULL
## $ axis.ticks.length.y : NULL
## $ axis.ticks.length.y.left : NULL
## $ axis.ticks.length.y.right : NULL
## $ axis.line : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ axis.line.x : NULL
## $ axis.line.x.top : NULL
## $ axis.line.x.bottom : NULL
## $ axis.line.y : NULL
## $ axis.line.y.left : NULL
## $ axis.line.y.right : NULL
## $ legend.background :List of 5
## ..$ fill : NULL
## ..$ colour : logi NA
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ legend.margin : 'margin' num [1:4] 4.5points 4.5points 4.5points 4.5points
## ..- attr(*, "unit")= int 8
## $ legend.spacing : 'simpleUnit' num 9points
## ..- attr(*, "unit")= int 8
## $ legend.spacing.x : NULL
## $ legend.spacing.y : NULL
## $ legend.key :List of 5
## ..$ fill : chr "white"
## ..$ colour : logi NA
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ legend.key.size : 'simpleUnit' num 1.2lines
## ..- attr(*, "unit")= int 3
## $ legend.key.height : NULL
## $ legend.key.width : NULL
## $ legend.text :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 0.8
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ legend.text.align : NULL
## $ legend.title :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 0
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ legend.title.align : NULL
## $ legend.position : num [1:2] 0 0
## $ legend.direction : NULL
## $ legend.justification : num [1:2] 0 0
## $ legend.box : NULL
## $ legend.box.just : NULL
## $ legend.box.margin : 'margin' num [1:4] 0cm 0cm 0cm 0cm
## ..- attr(*, "unit")= int 1
## $ legend.box.background : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ legend.box.spacing : 'simpleUnit' num 9points
## ..- attr(*, "unit")= int 8
## $ panel.background : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ panel.border : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ panel.spacing : 'simpleUnit' num 0lines
## ..- attr(*, "unit")= int 3
## $ panel.spacing.x : NULL
## $ panel.spacing.y : NULL
## $ panel.grid : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ panel.grid.major : NULL
## $ panel.grid.minor :List of 6
## ..$ colour : NULL
## ..$ size : 'rel' num 0.5
## ..$ linetype : NULL
## ..$ lineend : NULL
## ..$ arrow : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_line" "element"
## $ panel.grid.major.x : NULL
## $ panel.grid.major.y : NULL
## $ panel.grid.minor.x : NULL
## $ panel.grid.minor.y : NULL
## $ panel.ontop : logi FALSE
## $ plot.background : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ plot.title :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 1.2
## ..$ hjust : num 0
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 4.5points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.title.position : chr "panel"
## $ plot.subtitle :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 0
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 4.5points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.caption :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 0.8
## ..$ hjust : num 1
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 4.5points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.caption.position : chr "panel"
## $ plot.tag :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 1.2
## ..$ hjust : num 0.5
## ..$ vjust : num 0.5
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.tag.position : chr "topleft"
## $ plot.margin : 'margin' num [1:4] 4.5points 4.5points 4.5points 4.5points
## ..- attr(*, "unit")= int 8
## $ strip.background :List of 5
## ..$ fill : chr "grey85"
## ..$ colour : chr "grey20"
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ strip.background.x : NULL
## $ strip.background.y : NULL
## $ strip.placement : chr "inside"
## $ strip.text :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : chr "grey10"
## ..$ size : 'rel' num 0.8
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 3.6points 3.6points 3.6points 3.6points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ strip.text.x : NULL
## $ strip.text.y :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : num -90
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ strip.switch.pad.grid : 'simpleUnit' num 2.25points
## ..- attr(*, "unit")= int 8
## $ strip.switch.pad.wrap : 'simpleUnit' num 2.25points
## ..- attr(*, "unit")= int 8
## $ strip.text.y.left :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : num 90
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## - attr(*, "class")= chr [1:2] "theme" "gg"
## - attr(*, "complete")= logi TRUE
## - attr(*, "validate")= logi TRUE
Smaller numbers in zoom show less detail, while bigger numbers show more detail.As the zoom number gets bigger, the map becomes more detailed, so if you have a small area the zoom number can be bigger and thus more detailed, but if the area is bigger, the zoom number has to be smaller and less detailed.
get_stamenmap() in help and look at maptype). Include a map with one of the other map types.twincities <- get_stamenmap(
bbox = c(left = -93.4471, bottom = 44.8173, right = -92.7838, top = 45.1316),
maptype = "terrain-lines",
zoom = 11)
ggmap(twincities) + # creates the map "background"
geom_point(data = Starbucks,
aes(x = Longitude, y = Latitude),
alpha = 1,
size = 2,
color = "lightgreen") +
labs(title = "Starbucks in the Twin Cities") +
theme_map()
annotate() function (see ggplot2 cheatsheet).twincities <- get_stamenmap(
bbox = c(left = -93.4471, bottom = 44.8173, right = -92.7838, top = 45.1316),
maptype = "terrain-lines",
zoom = 11)
ggmap(twincities) + # creates the map "background"
geom_point(data = Starbucks,
aes(x = Longitude, y = Latitude),
alpha = 1,
size = 2,
color = "lightgreen") +
annotate(geom = "text", y = 44.9416, x = -93.16, label = "Macalester College") +
labs(title = "Starbucks in the Twin Cities") +
theme_map()
geom_map())The example I showed in the tutorial did not account for population of each state in the map. In the code below, a new variable is created, starbucks_per_10000, that gives the number of Starbucks per 10,000 people. It is in the starbucks_with_2018_pop_est dataset.
census_pop_est_2018 <- read_csv("https://www.dropbox.com/s/6txwv3b4ng7pepe/us_census_2018_state_pop_est.csv?dl=1") %>% #read csv into r and creates a new dataset called census_pop_est_2018
separate(state, into = c("dot","state"), extra = "merge") %>% #The state data was presented with a period preceding the state name. The separate function separates the period from the other characters.
select(-dot) %>% #selects all variables/columns except "dot"
mutate(state = str_to_lower(state)) #turns the state string into all lowercase letters
starbucks_with_2018_pop_est <- #creates new dataset
starbucks_us_by_state %>%
left_join(census_pop_est_2018,
by = c("state_name" = "state")) %>% #joins starbucks_us_by_state dataset with the census_pop dataset. since the starbucks_us dataset calls the state variable "state_name" and the census dataset calls the state variable "state", the by line matches those two variables to the same one.
mutate(starbucks_per_10000 = (n/est_pop_2018)*10000) #creates variable to show the number of Starbucks per 10,000 people per state
dplyr review: Look through the code above and describe what each line of code does.
Create a choropleth map that shows the number of Starbucks per 10,000 people on a map of the US. Use a new fill color, add points for all Starbucks in the US (except Hawaii and Alaska), add an informative title for the plot, and include a caption that says who created the plot (you!). Make a conclusion about what you observe.
#US states map information - coordinates used to draw borders
states_map <- map_data("state")
# map that colors state by number of Starbucks
starbucks_with_2018_pop_est %>%
ggplot() +
geom_map(map = states_map,
aes(map_id = state_name,
fill = n/est_pop_2018*10000)) +
geom_point(data = Starbucks %>%
filter(`Country` == "US") %>%
filter(`State/Province` != "AK") %>%
filter(`State/Province` != "HI"),
aes(x = Longitude, y = Latitude),
alpha = .3,
size = .1,
color = "goldenrod") +
expand_limits(x = states_map$long, y = states_map$lat) +
scale_fill_viridis_c(option = "plasma") +
theme_map() +
labs(title = "Starbucks per 10,000 people",
fill = "Starbucks per 10,000 People",
caption = "Plot created by Anna Leidner")
#Lighter colors (more Starbucks per 10,000 people) are related to the population size of a city, like in New York, the lighter yellow shows where New York City is, where there are going to be more Starbucks. California shows a similar pattern, where the two splotches of yellow are likely where San Francisco and Los Angeles are.
leaflet)tibble() function that has 10-15 rows of your favorite places. The columns will be the name of the location, the latitude, the longitude, and a column that indicates if it is in your top 3 favorite locations or not. For an example of how to use tibble(), look at the favorite_stp_by_lisa I created in the data R code chunk at the beginning.#Anna's favorite places
favorite_by_anna <- tibble(
place = c("Kimchi Tofu House", "Tono Pizzeria + Cheesesteak",
"Macalester College", "Science Museum of Minnesota", "Target Field",
"Saint Paul Home", "Riverside Park", "NYC Home",
"Jin Fong Restaurant", "The High Line", "Citi Field",
"Kate's Seafood", "Long Nook Beach"),
long = c( -93.22693673444148, -93.16733278846144,
-93.16905451640325, -93.09913377060474,
-93.27759701544593, -93.15993888846154,
-73.9729219893889, -73.9717327732488,
-73.97883524441367, -74.0039163349285,
-73.84583203092146, -70.11022135787704,
-70.03705415706891),
lat = c(44.97333972848076, 44.934273777055594,
44.93861924693568, 44.946322266714894,
44.9818947558888, 44.93189077914104,
40.801862889204585, 40.79972265717478,
40.78301103574647, 40.751173188177894,
40.75725834451115, 41.75483506515295,
42.02195492958253),
top3 = c("Not Top 3", "Not Top 3", "Top 3", "Not Top 3", "Not Top 3", "Not Top 3", "Top 3", "Top 3", "Not Top 3", "Not Top 3", "Not Top 3", "Not Top 3", "Not Top 3")
)
leaflet map that uses circles to indicate your favorite places. Label them with the name of the place. Choose the base map you like best. Color your 3 favorite places differently than the ones that are not in your top 3 (HINT: colorFactor()). Add a legend that explains what the colors mean.factpal <- colorFactor(topo.colors(3), favorite_by_anna$top3)
leaflet(data = favorite_by_anna) %>%
addProviderTiles(providers$Stamen.Terrain) %>%
addCircles(lng = ~long,
lat = ~lat,
label = ~place,
weight = 5,
opacity = 1,
color = ~factpal(top3)) %>%
addPolylines(lng = ~long,
lat = ~lat,
color = col2hex("darkred")) %>%
addLegend(pal = factpal,
values = ~top3,
opacity = 0.5,
title = NULL,
position = "bottomright")
Connect all your locations together with a line in a meaningful way (you may need to order them differently in the original data). I reordered the points so that the NYC Home, the home I grew up in, is the midpoint between the points in Massachusetts and Minnesota.
If there are other variables you want to add that could enhance your plot, do that now.
This section will revisit some datasets we have used previously and bring in a mapping component.
The data come from Washington, DC and cover the last quarter of 2014.
Two data tables are available:
Trips contains records of individual rentalsStations gives the locations of the bike rental stationsHere is the code to read in the data. We do this a little differently than usualy, which is why it is included here rather than at the top of this file. To avoid repeatedly re-reading the files, start the data import chunk with {r cache = TRUE} rather than the usual {r}. This code reads in the large dataset right away.
data_site <-
"https://www.macalester.edu/~dshuman1/data/112/2014-Q4-Trips-History-Data.rds"
Trips <- readRDS(gzcon(url(data_site)))
Stations<-read_csv("http://www.macalester.edu/~dshuman1/data/112/DC-Stations.csv")
Stations to make a visualization of the total number of departures from each station in the Trips data. Use either color or size to show the variation in number of departures. This time, plot the points on top of a map. Use any of the mapping tools you’d like.stationTrips <- Trips %>%
left_join(Stations,
by = c("sstation" = "name")) %>%
#select(sstation, client) %>%
group_by(lat, long) %>%
mutate(total = n())
#summarize(n = n())
washingtondc <- get_stamenmap(
bbox = c(left = -77.1869, bottom = 38.8107, right = -76.8374, top = 38.9684),
maptype = "terrain",
zoom = 12
)
ggmap(washingtondc) +
geom_point(data = stationTrips,
aes(x = long, y = lat, color = total),
size = .8) +
scale_color_viridis_c(option = "magma") +
theme_map() +
#theme(legend.background = element_blank()) +
labs(title = "Total Number of Departures By Station",
fill = guide_legend("Number of Departures"))
washingtondc <- get_stamenmap(
bbox = c(left = -77.1869, bottom = 38.8107, right = -76.8374, top = 38.9684),
maptype = "terrain",
zoom = 12
)
stationTrips <- stationTrips %>%
mutate(propcasual = mean(client == "Casual"))
ggmap(washingtondc) +
geom_point(data = stationTrips,
aes(x = long, y = lat, color = propcasual),
size = .8) +
scale_color_viridis_c(option = "magma") +
theme_map() +
labs(title = "Percentage of Departures by Client Type",
fill = "Proportion Casual Users")
#+
#theme(legend.background = element_blank())
I notice that in the map above, the proportion of Casual Clients is higher near the heart of that downtown area and where the National Mall is. One of the pale dots is near the Lincoln Memorial and the other is near the Washington Monument. This makes sense as they would be the areas with the highest population of tourists/casual users.
The following exercises will use the COVID-19 data from the NYT.
#covid19$state <- tolower(covid19$state)
covid19_state <- covid19 %>%
group_by(state) %>%
arrange(desc(date)) %>%
#mutate(cases = as.character(cases)) %>%
mutate(cases = as.integer(cases)) %>%
mutate(state = tolower(state)) %>%
slice(1)
states_map <- map_data("state")
covid19_state %>%
ggplot() +
geom_map(map = states_map,
aes(map_id = state,
fill = cases)) +
expand_limits(x = states_map$long, y = states_map$lat) +
theme_map() +
#scale_fill_viridis_c(option = "plasma") +
#scale_fill_viridis_c(option = "plasma", direction = -1) +
labs(title = "Cumulative COVID Cases in the US",
fill = "Cumulative Cases",
caption = "Plot Created by Anna Leidner")
In the map above, we see that the most recent cumulative number of COVID cases per state. The darker the color/the closes to dark purple, the higher the number of cumulative cases is. The results are to be expected as the states with the largest populations like California, Texas, Florida, and New York, have had the highest number of cumulative COVID cases. The map does not show how many COVID cases there are in relation to the population/does not take population into account.
census_pop_est_2018 <- read_csv("https://www.dropbox.com/s/6txwv3b4ng7pepe/us_census_2018_state_pop_est.csv?dl=1") %>% #read csv into r and creates a new dataset called census_pop_est_2018
separate(state, into = c("dot","state"), extra = "merge") %>% #The state data was presented with a period preceding the state name. The separate function separates the period from the other characters.
select(-dot) %>% #selects all variables/columns except "dot"
mutate(state = str_to_lower(state)) #turns the state string into all lowercase letters
covid19_state <- covid19 %>%
group_by(state) %>%
arrange(desc(date)) %>%
#mutate(cases = as.character(cases)) %>%
mutate(cases = as.integer(cases)) %>%
mutate(state = tolower(state)) %>%
slice(1)
covid19_10000 <- #creates new dataset
covid19_state %>%
left_join(census_pop_est_2018,
by = c("state")) #joins starbucks_us_by_state dataset with the census_pop dataset. since the starbucks_us dataset calls the state variable "state_name" and the census dataset calls the state variable "state", the by line matches those two variables to the same one.
#mutate(starbucks_per_10000 = (n/est_pop_2018)*10000) #creates variable to show the number of Starbucks per 10,000 people per state
covid19_10000 %>%
ggplot() +
geom_map(map = states_map,
aes(map_id = state,
fill = cases/est_pop_2018*10000)) +
expand_limits(x = states_map$long, y = states_map$lat) +
#scale_fill_viridis_c(option = "plasma") +
theme_map() +
labs(title = "Cumulative COVID Cases per 10,000 people",
fill = "Cases per 10,000",
caption = "Plot created by Anna Leidner")
These exercises use the datasets MplsStops and MplsDemo from the carData library. Search for them in Help to find out more information.
MplsStops dataset to find out how many stops there were for each neighborhood and the proportion of stops that were for a suspicious vehicle or person. Sort the results from most to least number of stops. Save this as a dataset called mpls_suspicious and display the table.mpls_suspicious <- MplsStops %>%
group_by(neighborhood) %>% #this finds total stops by neighborhood
#mutate(totneighbor = n()) %>%
#distinct(neighborhood, .keep_all=TRUE) %>%
mutate(stops = n(),
prop_suspicious = mean(problem == "suspicious")) %>%
#slice(1) %>% #do i need this
arrange(desc(stops)) #%>%
#select(neighborhood:prop_suspicious)
mpls_suspicious
leaflet map and the MplsStops dataset to display each of the stops on a map as a small point. Color the points differently depending on whether they were for suspicious vehicle/person or a traffic stop (the problem variable). HINTS: use addCircleMarkers, set stroke = FAlSE, use colorFactor() to create a palette.factpal <- colorFactor(topo.colors(5), MplsStops$problem)
leaflet(data = MplsStops) %>%
addProviderTiles(providers$Stamen.Terrain) %>%
addCircleMarkers(lng = ~long,
lat = ~lat,
label = ~neighborhood,
weight = 3,
opacity = 1,
stroke = FALSE,
color = ~factpal(problem),
radius = 1) %>%
addLegend(pal = factpal,
values = ~problem,
opacity = 0.5,
title = NULL,
position = "bottomright")
eval=FALSE. Although it looks like it only links to the .sph file, you need the entire folder of files to create the mpls_nbhd data set. These data contain information about the geometries of the Minneapolis neighborhoods. Using the mpls_nbhd dataset as the base file, join the mpls_suspicious and MplsDemo datasets to it by neighborhood (careful, they are named different things in the different files). Call this new dataset mpls_all.mpls_nbhd <- st_read("Minneapolis_Neighborhoods/Minneapolis_Neighborhoods.shp", quiet = TRUE)
mpls_all <- mpls_nbhd %>%
left_join(mpls_suspicious,
by = c("BDNAME" = "neighborhood")) %>%
left_join(MplsDemo,
by = c("BDNAME" = "neighborhood"))
mpls_all
leaflet to create a map from the mpls_all data that colors the neighborhoods by prop_suspicious. Display the neighborhood name as you scroll over it. Describe what you observe in the map.#pal2 <- colorFactor(topo.colors(5), mpls_all$prop_suspicious)
pal2 <- colorNumeric("magma",
domain = mpls_all$prop_suspicious)
leaflet(data = mpls_all) %>%
addProviderTiles(providers$Stamen.Terrain) %>%
addCircles(lng = ~long,
lat = ~lat,
label = ~BDNAME,
weight = 3,
opacity = 1,
color = ~pal2(prop_suspicious)) %>%
addLegend(pal = pal2,
values = ~prop_suspicious,
opacity = 0.5,
title = NULL,
position = "bottomright")
In the map, there is a clear lines separating different neighborhoods by different suspicious proportions. I would have to guess that the neighborhoods with the darker dots (smaller proportion of suspicious stops), are more likely to be White neighborhoods, while the neighborhoods with the more yellow dots (larger proportion of suspicious stops), are more likely to be neighborhoods with a larger population of people of color.
leaflet to create a map of your own choosing. Come up with a question you want to try to answer and use the map to help answer that question. Describe what your map shows.#Do the number of suspicious police stops change based on the demographics of the neighborhood?
#pal3 <- colorFactor(topo.colors(5), mpls_all$stops)
pal3 <- colorNumeric("magma",
domain = mpls_all$stops)
leaflet(mpls_all) %>%
addProviderTiles(providers$Esri.NatGeoWorldMap) %>%
addCircles(lng = ~long,
lat = ~lat,
color = ~pal3(stops),
label = ~race,
weight = .3,
opacity = .4) %>%
addLegend("topleft",
pal = pal3,
values = ~stops)
When looking at the above map, it seems as though the number of stops is affected by the population of the area, or density of commuters. The number of stops does seem loosely correlated with the suspicious proportion, but the correlation is not extremely strong or clear.
DID YOU REMEMBER TO UNCOMMENT THE OPTIONS AT THE TOP?